{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ME3B3OXET2GKAWBSI24GIYHSYA","short_pith_number":"pith:ME3B3OXE","schema_version":"1.0","canonical_sha256":"61361dbae49e8ca0583246b86460f2c000eed938a1624d0a7b4a1d40dbaee16b","source":{"kind":"arxiv","id":"2101.02055","version":2},"attestation_state":"computed","paper":{"title":"Geometric Entropic Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alaa Saade, Bernardo Avila Pires, Bilal Piot, Michal Valko, Mohammad Gheshlaghi Azar, R\\'emi Munos, Shantanu Thakoor, Thomas Mesnard, Tor Lattimore, Zhaohan Daniel Guo","submitted_at":"2021-01-06T14:15:07Z","abstract_excerpt":"Exploration is essential for solving complex Reinforcement Learning (RL) tasks. Maximum State-Visitation Entropy (MSVE) formulates the exploration problem as a well-defined policy optimization problem whose solution aims at visiting all states as uniformly as possible. This is in contrast to standard uncertainty-based approaches where exploration is transient and eventually vanishes. However, existing approaches to MSVE are theoretically justified only for discrete state-spaces as they are oblivious to the geometry of continuous domains. We address this challenge by introducing Geometric Entro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2101.02055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-06T14:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"352e6ef34ea50c2b574186c0f4df0840f6693c99b2383b73cf198db53070ca2c","abstract_canon_sha256":"17b45922926f42cf2b7e0dbb891b52c9df465b09dc64a6f0b806e122d1446761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:11.348306Z","signature_b64":"qfpkcapYyfWvmSV90B8LHgPHENpm4jME8zyNPoT0qpR4kJrk04EzNQa9YH03MpnP1PGcwP4WBx78RNl0FEgVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61361dbae49e8ca0583246b86460f2c000eed938a1624d0a7b4a1d40dbaee16b","last_reissued_at":"2026-07-05T02:05:11.347910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:11.347910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric Entropic Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alaa Saade, Bernardo Avila Pires, Bilal Piot, Michal Valko, Mohammad Gheshlaghi Azar, R\\'emi Munos, Shantanu Thakoor, Thomas Mesnard, Tor Lattimore, Zhaohan Daniel Guo","submitted_at":"2021-01-06T14:15:07Z","abstract_excerpt":"Exploration is essential for solving complex Reinforcement Learning (RL) tasks. Maximum State-Visitation Entropy (MSVE) formulates the exploration problem as a well-defined policy optimization problem whose solution aims at visiting all states as uniformly as possible. This is in contrast to standard uncertainty-based approaches where exploration is transient and eventually vanishes. However, existing approaches to MSVE are theoretically justified only for discrete state-spaces as they are oblivious to the geometry of continuous domains. We address this challenge by introducing Geometric Entro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02055","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.02055/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2101.02055","created_at":"2026-07-05T02:05:11.347966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02055v2","created_at":"2026-07-05T02:05:11.347966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02055","created_at":"2026-07-05T02:05:11.347966+00:00"},{"alias_kind":"pith_short_12","alias_value":"ME3B3OXET2GK","created_at":"2026-07-05T02:05:11.347966+00:00"},{"alias_kind":"pith_short_16","alias_value":"ME3B3OXET2GKAWBS","created_at":"2026-07-05T02:05:11.347966+00:00"},{"alias_kind":"pith_short_8","alias_value":"ME3B3OXE","created_at":"2026-07-05T02:05:11.347966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA","json":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA.json","graph_json":"https://pith.science/api/pith-number/ME3B3OXET2GKAWBSI24GIYHSYA/graph.json","events_json":"https://pith.science/api/pith-number/ME3B3OXET2GKAWBSI24GIYHSYA/events.json","paper":"https://pith.science/paper/ME3B3OXE"},"agent_actions":{"view_html":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA","download_json":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA.json","view_paper":"https://pith.science/paper/ME3B3OXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02055&json=true","fetch_graph":"https://pith.science/api/pith-number/ME3B3OXET2GKAWBSI24GIYHSYA/graph.json","fetch_events":"https://pith.science/api/pith-number/ME3B3OXET2GKAWBSI24GIYHSYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA/action/storage_attestation","attest_author":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA/action/author_attestation","sign_citation":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA/action/citation_signature","submit_replication":"https://pith.science/pith/ME3B3OXET2GKAWBSI24GIYHSYA/action/replication_record"}},"created_at":"2026-07-05T02:05:11.347966+00:00","updated_at":"2026-07-05T02:05:11.347966+00:00"}